target-cart-mcp
An MCP server for searching Target products and generating Shopping Cart Share links from a list of TCINs.
README
target-cart-mcp
An MCP server for searching Target products and generating Shopping Cart Share links from a list of TCINs.
Forked from @striderlabs/mcp-target (MIT). The upstream package exposes browser-session tools (login, add-to-cart, checkout, orders) that are unnecessary for agent-driven cart building and tend to confuse LLM agents into attempting them. This fork removes those tools, patches the browser automation layer for container stability, and adds a native create_share_a_cart_link tool backed by the Shopping Cart Share Firebase API.
Tools
| Tool | Description |
|---|---|
search_products |
Search Target products by keyword, category, price range, or sort order |
get_product |
Get detailed product info (price, description, availability) by URL or TCIN |
check_store_availability |
Check in-store availability for a TCIN at a given zip code |
create_share_a_cart_link |
Build a Shopping Cart Share link from a list of TCINs — returns a shoppingcartshare.com/shared/cart/XXXXX URL |
Changes from upstream
- Removed tools:
status,login,logout,add_to_cart,view_cart,clear_cart,checkout,get_orders,track_order - Added tool:
create_share_a_cart_link— POSTs to the Shopping Cart Share Firebase backend and returns a shareable cart URL - Browser patches: removed
channel: "chrome"launch arg (crashes in containers without real Chrome), added dead-browser detection + automatic reset on crash, added memory-saving Chromium flags for low-memory containers, 45s idle close timer
Usage
Docker Compose
services:
target-cart-mcp:
image: target-cart-mcp:latest
build: .
container_name: target-cart-mcp
volumes:
- ./data/.striderlabs:/root/.striderlabs
restart: unless-stopped
shm_size: '256m'
deploy:
resources:
limits:
memory: 2G
The server exposes a Streamable HTTP MCP endpoint at http://localhost:8000/mcp.
MCP client config (openclaw / Claude Desktop)
{
"mcp": {
"servers": {
"target": {
"url": "http://target-cart-mcp:8000/mcp",
"transport": "streamable-http"
}
}
}
}
Using create_share_a_cart_link
The returned URL (shoppingcartshare.com/shared/cart/XXXXX) opens a cart preview page. Clicking Use Cart with the Shopping Cart Share browser extension installed will import the items into your Target cart.
{
"tool": "create_share_a_cart_link",
"arguments": {
"items": [
{ "tcin": "12345678", "title": "Product Name", "quantity": 2, "image": "https://..." }
],
"cart_title": "Weekly Groceries"
}
}
Building
docker compose build
docker compose up -d
License
MIT — derived from @striderlabs/mcp-target (MIT).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.